[求助]新手求助~（关于初级的神经网络问题） [复制链接]

各位大虾，我在网上看到的教程里的一个程序段，本来想要试试看的： G6X5`eLQ  
net=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd'); o9Tsyjbj  
net.trainParam.show = 50; 5+/XO>P1m|  
net.trainParam.lr = 0.05; )%hW3w  
net.trainParam.epochs = 300; 6Zv-kG  
net.trainParam.goal = 1e-5; mC'<Ov<eJ  
p = [-1 -1 2 2;0 5 0 5]; O/oLQoH  
t = [-1 -1 1 1]; +rKV*XX@  
net=train(net,p,t); YOY2K%o  
TRAINGD, Epoch 0/300, MSE 1.59423/1e-05, Gradient 2.76799/1e-10 \CYKj_c  
TRAINGD, Epoch 50/300, MSE 0.00236382/1e-05, Gradient 0.0495292/1e-10 q oz[x  
TRAINGD, Epoch 100/300, MSE 0.000435947/1e-05, Gradient 0.0161202/1e-10 SYgkYR  
TRAINGD, Epoch 150/300, MSE 8.68462e-05/1e-05, Gradient 0.00769588/1e-10 nDz.61$[  
TRAINGD, Epoch 200/300, MSE 1.45042e-05/1e-05, Gradient 0.00325667/1e-10 ~vMJ?P@  
TRAINGD, Epoch 211/300, MSE 9.64816e-06/1e-05, Gradient 0.00266775/1e-10 ,fhK  
TRAINGD, Performance goal met. 1gX$U00:  
a = sim(net,p) =
@d->d  
plot(p,t,p,a,'o') tjcsT>  
但是为什么老是报错： "lB%"}  
??? Input argument "net" is undefined. u_Xp
\RJ